为陪伴机器人设计可理解的非语言沟通方式，提升老年人认知匹配度。
What Does a Meow Mean? In Search of Intuitively Understandable Communication by a Nonverbal Companion Robot
- 结合猫叫声与屏幕图标，设计双模态非语言信号。
- 视觉+听觉组合下识别准确率达85%以上，纯听觉时反而更高。
- 情感强烈时声音信号更有效，适合情绪表达场景。
独居老年人面临诸多挑战，机器人可通过提醒、引导活动或提供慰藉来协助。在开发一款功能有限的猫形陪伴机器人过程中，我们设计了一套非语言通信信号，包含听觉（猫叫声）和视觉（小屏图标）。通过混合方法、以用户为中心的研究，先进行小规模预实验，再由老年群体焦点小组提出修改建议。随后开展大规模在线实验，测试65岁以上成年人对机器人意图的理解能力。结果显示：当视听信号同时存在时，识别准确率较高；缺少视觉信号时，准确率常下降；而缺少听觉信号时，准确率有时反而上升。因此，听觉信号在表达强烈情绪（如被抚摸时发出呼噜声）时尤为有效。
原文摘要 · Abstract (English)
Older adults living alone have a number of challenges, and robots can help with some of them--by providing reminders, initiating activity, or offering comfort. As part of developing a cat robot with limited assistive functions, we designed a set of nonverbal communication signals, both auditory (cat sounds) and visual (icons on a small display). To evaluate these signals we used a mixed-methods, user-centered approach. After a pilot study, a focus group with older adults suggested revisions to the initial signal set. A large-sample online experiment then tested whether adults over the age of 65 could accurately infer the robot's communicative intentions. When both visual and auditory signals were present, accuracy was high. When visual signals were absent, accuracy often decreased; when auditory signals were absent, accuracy sometimes increased. So the auditory signals were less helpful, except when the robot conveyed strong sentiments (e.g., purring while being petted).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。